Can it run?
Runs well
Using Q4_K_M in Ollama
Fit status
Runs well
Decode
273.5 tok/s
TTFT
708 ms
Safe context
81K
Memory
56.8 GB / 288.0 GB
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Agentic Coding | C | Runs well | 273.5 tok/s | 1029 ms | 148K |
| Chat | C | Runs well | 273.5 tok/s | 386 ms | 43K |
| Coding | C | Runs well | 273.5 tok/s | 708 ms | 81K |
| RAG | C | Runs well | 273.5 tok/s | 1287 ms | 148K |
| Reasoning | C | Runs well | 273.5 tok/s | 836 ms | 81K |
How Qwen3.5 35B A3B (35B params) fits at each quantization level on AMD Instinct MI350X 288GB (288.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 13.7 GB | Low | D30 |
Q3_K_S | 3 | 17.2 GB | Low | D31 |
NVFP4 | 4 |
huggingface-cli download hf-lmstudio-community--qwen3-5-35b-a3b-gguf19.6 GB |
| Medium |
| D31 |
Q4_K_M | 4 | 21.3 GB | Medium | D31 |
Q5_K_M | 5 | 25.2 GB | High | D31 |
Q6_K | 6 | 28.7 GB | High | D32 |
Q8_0 | 8 | 37.5 GB | Very High | D32 |
F16Best for your GPU | 16 | 71.8 GB | Maximum | D35 |